In [1]:
import pandas as pd
pd.plotting.register_matplotlib_converters()
import matplotlib.pyplot as plt
%matplotlib inline
import seaborn as sns
import numpy as np
from datetime import datetime as dt
print("Setup Complete")

Setup Complete
In [2]:
from itertools import cycle
import plotly.graph_objects as go
import plotly.express as px
from plotly.subplots import make_subplots
import plotly.figure_factory as ff
In [3]:
dataset = pd.read_csv('C:/Users/rajat/Downloads/TSLA(16-21).csv')
dataset.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1258 entries, 0 to 1257
Data columns (total 7 columns):
 #   Column     Non-Null Count  Dtype  
---  ------     --------------  -----  
 0   Date       1258 non-null   object 
 1   Open       1258 non-null   float64
 2   High       1258 non-null   float64
 3   Low        1258 non-null   float64
 4   Close      1258 non-null   float64
 5   Adj Close  1258 non-null   float64
 6   Volume     1258 non-null   int64  
dtypes: float64(5), int64(1), object(1)
memory usage: 68.9+ KB
In [4]:
dataset['Date'] = pd.to_datetime(dataset['Date'])
dataset.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1258 entries, 0 to 1257
Data columns (total 7 columns):
 #   Column     Non-Null Count  Dtype         
---  ------     --------------  -----         
 0   Date       1258 non-null   datetime64[ns]
 1   Open       1258 non-null   float64       
 2   High       1258 non-null   float64       
 3   Low        1258 non-null   float64       
 4   Close      1258 non-null   float64       
 5   Adj Close  1258 non-null   float64       
 6   Volume     1258 non-null   int64         
dtypes: datetime64[ns](1), float64(5), int64(1)
memory usage: 68.9 KB
In [5]:
df2= dataset.groupby(dataset['Date'].dt.strftime('%B'))[['Open','Close']].mean()
new_order = ['January', 'February', 'March', 'April', 'May', 'June', 'July', 'August', 
             'September', 'October', 'November', 'December']
df2 = df2.reindex(new_order, axis=0)
df2
Out[5]:
Open Close
Date
January 211.862118 212.589568
February 227.558569 227.040441
March 194.185782 193.161236
April 205.595030 205.671611
May 181.159451 180.826095
June 204.369197 204.726543
July 226.404302 226.023074
August 173.212144 174.174936
September 129.064456 128.870416
October 129.469280 128.815189
November 137.678000 137.957262
December 183.599535 185.258544
In [6]:
fig = go.Figure()
fig.add_trace(go.Bar(
    x=df2.index,
    y=df2['Open'],
    name='Stock Price HIGH',
    marker_color='rgb(0, 153, 204)'
))
fig.add_trace(go.Bar(
    x=df2.index,
    y=df2['Close'],
    name='Stock Price LOW',
    marker_color='rgb(255, 128, 0)'
))

fig.update_layout(barmode='group', 
                  title='Monthly mean of High and Low value of Stocks')
In [7]:
df3= dataset.groupby(dataset['Date'].dt.strftime('%B'))[['High']].max()
df3 = df3.reindex(new_order, axis=0)

df4= dataset.groupby(dataset['Date'].dt.strftime('%B'))[['Low']].min()
df4 = df4.reindex(new_order, axis=0)

new_order = ['January', 'February', 'March', 'April', 'May', 'June', 'July', 'August', 
             'September', 'October', 'November', 'December']
In [8]:
fig1 = go.Figure()
fig1.add_trace(go.Scatter(
    x=df3.index,
    y=df3['High'],
    mode = 'lines',
    name='Max Stock',
    marker_color='rgb(0, 153, 204)'
))
fig1.add_trace(go.Scatter(
    x=df4.index,
    y=df4['Low'],
    mode = 'lines',
    name='Min Stock',
    marker_color='rgb(255, 128, 0)'
))
fig1.update_layout(
    height=800,
    showlegend=True,
    title_text="Monthly Max and Min Stock trend",
)

fig1.show()
In [9]:
df = dataset.drop('Volume', axis=1)
In [10]:
def plot_line(dataset,title):
    fig = px.line(dataset, x= "Date", y=dataset.columns,                                   
                  title=title)
    fig.update_xaxes(
        dtick="M1",
        tickformat="%b\n%Y")
    fig.show()
In [11]:
dfm1 = df[df['Date']<'2017-08-16']
plot_line(dfm1,'Stock variation in first recorded yr(2016-08-16 to 2017-08-16)')
In [12]:
dfm2 = df[(df['Date'] > '2017-08-16') & (df['Date'] < '2018-08-16')]
plot_line(dfm2,'Stock variation in second recorded yr(2017-08-16 to 2018-08-16)')
In [13]:
dfm3 = df[(df['Date'] > '2018-08-16') & (df['Date'] < '2019-08-16')]
plot_line(dfm3,'Stock variation in third recorded yr(2018-08-16 to 2019-08-16)')
In [14]:
dfm4 = df[(df['Date'] > '2019-08-16') & (df['Date'] < '2020-08-16')]
plot_line(dfm4,'Stock variation in fourth recorded yr(2019-08-16 to 2020-08-16)')
In [15]:
dfm5 = df[(df['Date'] > '2020-08-16') & (df['Date'] < '2021-08-13')]
plot_line(dfm5, 'Stock variation in fifth recorded yr(2020-08-16 to 2021-08-13)')
In [16]:
def plot_line2(dst, title):
    fig = px.line(dst, x= "Date", y=dst.Volume,                                   
                  title=title)
    fig.update_xaxes(
        dtick="M1",
        tickformat="%b\n%Y")
    fig.show()
In [17]:
dfv1 = dataset[dataset['Date']<'2017-08-16']
plot_line2(dfv1,'Volume variation in first recorded yr(2016-08-16 to 2017-08-16)')
In [18]:
dfv2 = dataset[(dataset['Date'] > '2017-08-16') & (dataset['Date'] < '2018-08-16')]
plot_line2(dfv2,'Volume variation in second recorded yr(2017-08-16 to 2018-08-16)')
In [19]:
dfv3 = dataset[(dataset['Date'] > '2018-08-16') & (dataset['Date'] < '2019-08-16')]
plot_line2(dfv3,'Volume variation in third recorded yr(2018-08-16 to 2019-08-16)')
In [20]:
dfv4 = dataset[(dataset['Date'] > '2019-08-16') & (dataset['Date'] < '2020-08-16')]
plot_line2(dfv4,'Volume variation in fourth recorded yr(2019-08-16 to 2020-08-16)')
In [21]:
dfv5 = dataset[(dataset['Date'] > '2020-08-16') & (dataset['Date'] < '2021-08-13')]
plot_line2(dfv5, 'Volume variation in fifth recorded yr(2020-08-16 to 2021-08-13)')
In [22]:
fig = px.line(dataset, x='Date', y=dataset['Close'].rolling(window=20).mean())
fig.show()
fig1 = px.line(dataset, x='Date', y=dataset['Volume'].rolling(window=20).mean())
fig1.show()